Generalised linear models for multi-class classification problems are one of the fundamental
building blocks of modern machine learning tasks. In this manuscript, we characterise the …

This paper investigates the asymptotic behavior of the soft-margin and hard-margin support
vector machine (SVM) classifiers for simultaneously high-dimensional and numerous data …

Research on near-term quantum machine learning has explored how classical machine
learning algorithms endowed with access to quantum kernels (similarity measures) can …

Randomly perturbing networks during the training process is a commonly used approach to
improving generalization performance. In this paper, we present a theoretical study of one …

While classical in many theoretical settings—and in particular in statistical physics-inspired
works—the assumption of Gaussian iid input data is often perceived as a strong limitation in …

Federated learning is emerging as a privacy-preserving model training approach in
distributed edge applications. As such, most edge deployments are heterogeneous in …

While classical in many theoretical settings-and in particular in statistical physics-inspired
works-the assumption of Gaussian iid input data is often perceived as a strong limitation in …

Large-margin classifiers are popular methods for classification. We derive the asymptotic
expression for the generalization error of a family of large-margin classifiers in the limit of …

Abstract Recently, Vladimir Vapnik et al. proposed a generalization-memorization kernel for
SVC, which significantly improves the memorization and generalization performance of …

Margin-based classifiers have been popular in both machine learning and statistics for
classification problems. Since a large number of classifiers are available, one natural …